Digital central optimization method and system

Abstract

The invention provides a digital center optimization method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining enterprise business process data, including order processing, inventory management, supply chain coordination and customer feedback, and carrying out the preprocessing of the enterprise business process data, so as to obtain a processed data pool; constructing a digital transformation center model according to the processed data pool; defining a fitness function to evaluate the performance of the current digital transformation hub model; and performing iterative optimization on the digital transformation center model through selection, crossover and mutation operations until a preset number of iterations is reached, so as to obtain an optimized digital transformation center model. According to the method, the digital transformation center model is constructed and optimized, so that the enterprise business process is effectively adjusted, the order processing, inventory management and supply chain coordination efficiency is improved, and the optimization of digital transformation is realized.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a digital hub optimization method and system. Background Art

[0002] Although traditional data processing solutions play an important role in the digital transformation of enterprises, they sometimes have some defects in practical applications.

[0003] Traditional solutions may not be able to fully capture all key data in the order processing process. For example, customers' special needs, order modification records, logistics tracking information, etc. may not be fully recorded. This leads to a lack of comprehensive and accurate information support when processing orders, increasing the risk of processing errors and delays.

[0004] Traditional data processing solutions rely on manual input and updating of data, which results in untimely data updates. In a high-speed business environment, enterprises make decisions based on partial or outdated information, which undoubtedly increases the risk of decision-making errors. For example, scheduling production or procurement based on old inventory information may lead to inventory backlogs or stock-outs. Traditional solutions lack automated and intelligent processing capabilities and cannot respond quickly to market changes and customer needs. This leads to inefficiencies in processing large orders and makes it difficult for enterprises to maintain their competitive advantage. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a digital hub optimization method and system to improve the efficiency and effectiveness of enterprise digital transformation.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0007] In a first aspect, a digital hub optimization method is provided, the method comprising:

[0008] Acquire enterprise business process data, including order processing, inventory management, supply chain coordination, and customer feedback, and pre-process the enterprise business process data to obtain a processed data pool;

[0009] Build a digital transformation hub model based on the processed data pool;

[0010] Define a fitness function to evaluate the performance of the current digital transformation hub model;

[0011] Through selection, crossover and mutation operations, the digital transformation hub model is iteratively optimized until a preset number of iterations is reached to obtain an optimized digital transformation hub model;

[0012] Based on the optimized digital transformation hub model, the company's existing business processes are adjusted, including redesigning the order processing process, optimizing inventory management solutions, and improving supply chain coordination methods to achieve optimization of the digital transformation hub.

[0013] Furthermore, the enterprise business process data is obtained, including order processing, inventory management, supply chain coordination, and customer feedback, and the enterprise business process data is pre-processed to obtain a processed data pool, including:

[0014] Extract new data generated in the business process from the enterprise business process data source in real time, and clean the extracted new data to obtain cleaned data;

[0015] Based on common identification, the cleaned data is merged across data sources to form a processed data pool containing order processing, inventory management, supply chain coordination and customer feedback information.

[0016] Furthermore, based on the processed data pool, a digital transformation hub model is constructed, including:

[0017] Based on the constructed data pool, the data of each business link including order processing, inventory management, supply chain coordination and customer feedback are integrated to obtain the integrated data;

[0018] Determine the framework of the digital transformation hub model based on the integrated data and enterprise business processes, including determining the nodes and edges in the model;

[0019] Map the integrated data to the digital transformation hub model framework to build the digital transformation hub model.

[0020] Furthermore, the calculation formula of the fitness function is:

[0021]

[0022] Among them, F represents the fitness value; w3 represents the weight of inventory cost; w4 represents the weight of supply chain satisfaction; C i represents the inventory cost of the i-th iteration; η represents a constant; ζ represents the adjustment parameter of the holding cost; I h represents holding cost; L represents logistics efficiency; θ represents the adjustment parameter of supply chain satisfaction; S s represents supply chain satisfaction; ξ represents the adjustment parameter of logistics cost; It represents the parameter of balanced logistics efficiency; e represents the base of natural logarithm.

[0023] Further, the digital transformation central model is iteratively optimized through selection, crossover and mutation operations until a preset number of iterations is reached to obtain an optimized digital transformation central model, including:

[0024] Creating an initial population of multiple candidate solutions for the digital transformation hub model, where each candidate solution is represented as a set of parameters;

[0025] Each candidate solution is evaluated using the fitness function and the fitness value of the candidate solution is determined from the current population as the parent;

[0026] Perform a crossover operation on the determined parent candidate solution to generate a new child candidate solution to obtain a child candidate solution containing new features;

[0027] Perform mutation operation on the offspring candidate solution, and use the fitness function to evaluate the newly generated offspring candidate solution to determine the corresponding fitness value;

[0028] According to the fitness value, the final candidate solution is determined and the population is updated until the preset number of iterations is reached. According to the fitness value of the candidate solution, the optimized digital transformation central model is obtained.

[0029] Furthermore, according to the optimized digital transformation hub model, the company's existing business processes are adjusted, including redesigning the order processing process, optimizing the inventory management plan, and improving the supply chain coordination method to achieve the optimization of the digital transformation hub, including:

[0030] According to the optimized digital transformation hub model, the order processing process is reconstructed to obtain the reconstructed order processing process;

[0031] Calculate the economic order quantity based on the reconstructed order processing flow and historical sales data to determine the inventory plan, and set the inventory quantity and replenishment cycle based on the inventory plan;

[0032] Through the supply chain management system, the execution of the reconstructed order processing process and inventory plan is evaluated to obtain the evaluation results;

[0033] Based on the evaluation results, the digital transformation hub model and business processes are continuously optimized and adjusted to achieve optimization of the digital transformation hub.

[0034] Furthermore, the economic order quantity is calculated as:

[0035]

[0036] Where Q represents the economic order quantity; D represents the annual demand; S represents the fixed cost of each order; C pIt is expressed as the additional processing cost for each order; H represents the basic annual holding cost per unit of goods; C h It represents the additional cost per unit of commodity due to the variability of holding costs; V h The coefficient representing the variability of holding costs; C s represents the cost of each out-of-stock event; R represents the expected out-of-stock frequency.

[0037] In a second aspect, a digital hub optimization system includes:

[0038] The acquisition module is used to acquire enterprise business process data, including order processing, inventory management, supply chain coordination, and customer feedback, and pre-process the enterprise business process data to obtain a processed data pool; build a digital transformation hub model based on the processed data pool; define a fitness function to evaluate the performance of the current digital transformation hub model;

[0039] The processing module is used to iteratively optimize the digital transformation hub model through selection, crossover and mutation operations until a preset number of iterations is reached to obtain the optimized digital transformation hub model; according to the optimized digital transformation hub model, the company's existing business processes are adjusted, including redesigning the order processing process, optimizing the inventory management plan, and improving the supply chain coordination method, so as to achieve the optimization of the digital transformation hub.

[0040] According to a third aspect, a computing device includes:

[0041] one or more processors;

[0042] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0043] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0044] The above solution of the present invention includes at least the following beneficial effects:

[0045] By obtaining enterprise business process data, including order processing, inventory management, supply chain coordination, customer feedback, etc., enterprises can have a more comprehensive and accurate information foundation. These data are pre-processed to form a data pool. The digital transformation hub model can reflect the status and changes of the enterprise's business processes in real time and provide immediate decision support for management. This helps enterprises respond quickly to the rapidly changing market environment and seize business opportunities. According to the optimized digital transformation hub model, enterprises can redesign existing business processes, such as simplifying and automating order processing processes. This helps reduce human errors and improve work efficiency. By optimizing inventory management solutions, enterprises can more accurately predict inventory needs and avoid inventory backlogs and out-of-stock phenomena. This helps reduce inventory costs and improve capital turnover.

[0046] Improving the supply chain coordination method can strengthen the communication and collaboration between enterprises and suppliers and customers, and improve the overall efficiency of the supply chain. This helps to shorten the product delivery cycle and improve customer satisfaction. The digital hub optimization method is an important part of the digital transformation of enterprises, which helps to promote the overall development of enterprises in the direction of digitalization and intelligence. This helps enterprises to occupy a favorable position in market competition and enhance their competitiveness. Through the optimization of the digital transformation hub, enterprises can discover new business models and market opportunities. For example, customer behavior prediction and personalized recommendations based on big data analysis can bring new growth points to enterprises. Through the optimized digital transformation hub model, enterprises can respond to customer needs and changes more quickly. This helps to improve customer satisfaction and loyalty and consolidate the market position of enterprises. The optimization of the digital transformation hub can also help enterprises improve service quality, such as improving service efficiency and accuracy through automated and intelligent service methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of a digital hub optimization method provided by an embodiment of the present invention.

[0048] Figure 2 It is a schematic diagram of a digital hub optimization system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0050] like Figure 1As shown, an embodiment of the present invention provides a digital hub optimization method, the method comprising the following steps:

[0051] Step 11, obtaining enterprise business process data, including order processing, inventory management, supply chain coordination, and customer feedback, and pre-processing the enterprise business process data to obtain a processed data pool;

[0052] Step 12: Build a digital transformation hub model based on the processed data pool;

[0053] Step 13, define a fitness function to evaluate the performance of the current digital transformation hub model;

[0054] Step 14, iteratively optimizing the digital transformation hub model through selection, crossover and mutation operations until a preset number of iterations is reached to obtain an optimized digital transformation hub model;

[0055] Step 15: Adjust the company’s existing business processes based on the optimized digital transformation hub model, including redesigning the order processing process, optimizing inventory management solutions, and improving supply chain coordination methods to achieve optimization of the digital transformation hub.

[0056] In an embodiment of the present invention, the comprehensiveness and accuracy of the data are ensured by comprehensively acquiring enterprise business process data, including order processing, inventory management, supply chain coordination, customer feedback, etc. The preprocessing process can eliminate noise and outliers in the data to ensure the consistency and reliability of the data. The digital transformation hub model can model the business processes of the enterprise, allowing the enterprise to more clearly understand the overall picture of its business process and the relationship between each link. By defining the fitness function, the enterprise can clarify the goals of digital hub optimization, such as improving efficiency, reducing costs, etc., so as to optimize more targeted.

[0057] Through selection, crossover and mutation operations, the digital transformation hub model is iteratively optimized to continuously improve the performance and adaptability of the model. Based on the optimized digital transformation hub model, enterprises can adjust and optimize existing business processes, such as redesigning order processing processes and optimizing inventory management solutions. Process optimization can eliminate waste and bottlenecks and improve the efficiency and response speed of business processes.

[0058] In a preferred embodiment of the present invention, the above step 11, obtaining enterprise business process data, including order processing, inventory management, supply chain coordination, and customer feedback, and pre-processing the enterprise business process data to obtain a processed data pool, may include:

[0059] Step 121, extracting new data generated in the business process from the enterprise business process data source in real time, and cleaning the extracted new data to obtain cleaned data;

[0060] Step 122, based on the common identifier, the cleaned data is merged across data sources to form a processed data pool containing order processing, inventory management, supply chain coordination and customer feedback information.

[0061] In an embodiment of the present invention, new data generated in the business process is extracted from the enterprise business process data source in real time to ensure the timeliness and accuracy of the data. The extracted data covers multiple aspects such as order processing, inventory management, supply chain coordination and customer feedback, ensuring the comprehensiveness and integrity of the data. The extracted new data is cleaned to remove noise and outliers in the data to ensure the accuracy and reliability of the data. This step usually includes operations such as data verification, format conversion, and missing value processing. Convert the data into a unified format and standard. For example, unify the date format, number format, etc. to ensure data consistency.

[0062] The cleaned data is merged across data sources based on common identifiers (such as order numbers, customer IDs, etc.). This step usually relies on data matching and association techniques, such as key-value joins, fuzzy matching, etc. The merged data forms a processed data pool that contains order processing, inventory management, supply chain coordination, and customer feedback information.

[0063] Through real-time extraction and data cleaning, the timeliness and accuracy of data are ensured, providing reliable data support for corporate decision-making. Data standardization improves the consistency and comparability of data, making it easier for companies to conduct data analysis and mining. Comprehensive data acquisition and merging enable companies to more clearly understand the overall picture of their business processes and the relationship between each link, helping to identify bottlenecks and problems in business processes. Data-based business process optimization can eliminate waste and bottlenecks, and improve the efficiency and response speed of business processes.

[0064] By optimizing inventory management and supply chain coordination, companies can reduce operating costs and improve profitability. For example, data-based inventory forecasting and replenishment strategies can reduce inventory backlogs and stockouts. Data-driven decision making can reduce the cost of human errors and misguided decisions. By analyzing customer feedback information, companies can better understand customer needs and expectations, thereby providing more personalized products and services. Optimized business processes can respond to customer needs and changes more quickly, improving customer satisfaction and loyalty.

[0065] When specifically applied, the above content specifically includes:

[0066] Use API interfaces to capture new data generated during the business process in real time. The extracted data covers multiple aspects such as order processing (such as order status, order amount), inventory management (such as inventory quantity, inventory location), supply chain coordination (such as supplier information, logistics information) and customer feedback (such as customer satisfaction, customer suggestions). Check the completeness, accuracy and consistency of the data, such as verifying whether the order amount is a reasonable value and whether the date format is correct. Convert data from different data sources to a unified format, such as unifying the date format to "YYYY-MM-DD" and the number format to two decimal places. For missing data, fill it according to business logic (such as using default values, the previous valid value, etc.) or mark it as missing. Establish data standards to ensure that all data follows the same format and rules. Use key-value connection, fuzzy matching and other technologies to merge the cleaned data across data sources based on common identifiers (such as order number, customer ID, etc.). The merged data forms a processed data pool containing order processing, inventory management, supply chain coordination and customer feedback information, providing high-quality data input for subsequent digital transformation and business process optimization.

[0067] Taking e-commerce companies as an example, their business process data sources may include order management systems, inventory management systems, supply chain management systems, and customer feedback systems. When applying the above steps, the specific operations are:

[0068] Extract order status, order amount and other data from the order management system in real time.

[0069] Extract data such as inventory quantity, inventory location, etc. from the inventory management system in real time.

[0070] Extract supplier information, logistics information and other data from the supply chain management system in real time.

[0071] Extract customer satisfaction, customer suggestions and other data from the customer feedback system in real time.

[0072] Verify the extracted data to ensure data integrity and accuracy. For example, check whether the order amount is a positive number and whether the date format is "YYYY-MM-DD". Convert the data in different data sources to ensure data consistency. For example, unify the inventory quantity into integers and customer satisfaction into a score of 1-5. Fill or mark missing data. For example, for missing order status, it can be marked as "unknown". Establish data standards, such as date format, number format, etc. Convert and process all data according to the established standards to ensure data consistency and comparability. Use key-value connection technology to merge the data in the order management system with the data in the inventory management system and supply chain management system according to the order number. Merge the data in the customer feedback system with the data in the order management system according to the customer ID. The merged data forms a processed data pool containing order processing, inventory management, supply chain coordination and customer feedback information, providing high-quality data support for the digital transformation and business process optimization of e-commerce companies.

[0073] In a preferred embodiment of the present invention, the above step 12, constructing a digital transformation hub model based on the processed data pool, may include:

[0074] Step 125, integrating the data of each business link of order processing, inventory management, supply chain coordination, and customer feedback according to the constructed data pool to obtain integrated data;

[0075] Step 126, determining the framework of the digital transformation hub model based on the integrated data and enterprise business processes, including determining nodes and edges in the model;

[0076] Step 127, map the integrated data into the digital transformation central model framework to construct the digital transformation central model.

[0077] In an embodiment of the present invention, data from various business links such as order processing, inventory management, supply chain coordination, and customer feedback. These data are integrated from different sources into a unified data storage. Based on the integrated data and enterprise business processes, the framework of the digital transformation hub model is determined. This framework includes multiple nodes and edges, where nodes represent business entities or processes, and edges represent the relationships and interactions between them. Nodes may include orders, inventory, suppliers, customers, etc., and edges may represent the association between orders and inventory, transactions between suppliers and customers, etc. The integrated data is mapped to the digital transformation hub model framework. This includes associating data with corresponding nodes and edges, and ensuring the accuracy and timeliness of the data. Centralized management of data and efficient collaboration of business. By integrating data from various business links, the model can provide a global perspective, enabling enterprises to monitor and analyze business operations in real time. At the same time, the nodes and edges in the model represent the relationship between business entities and processes, allowing enterprises to have a clearer understanding of the details and bottlenecks of business operations.

[0078] Specifically, when an order is created, the model automatically updates inventory information and triggers the supply chain coordination process. At the same time, customer feedback data will also be integrated into the model to provide companies with real-time insights into product and service quality. The flow and interaction of these data in the model enables efficient business collaboration and centralized data management.

[0079] Through the digital transformation hub model, enterprises can automate and intelligentize business processes, reduce manual intervention and errors, and thus improve operational efficiency. The real-time monitoring and analysis functions in the model enable enterprises to promptly discover and solve problems in business operations to avoid delays and losses. The digital transformation hub model can optimize inventory management, reduce inventory backlogs and waste, and thus reduce inventory costs. Through the optimization of supply chain coordination, enterprises can reduce transportation and procurement costs and further improve cost-effectiveness. The customer feedback data in the model enables enterprises to understand customer needs and opinions in a timely manner, thereby improving product and service quality and enhancing customer satisfaction. Through digital transformation, enterprises can provide more convenient and efficient services, such as online shopping and online payment, to enhance customer experience. The digital transformation hub model provides enterprises with rich data resources and analysis tools, enabling them to make decisions based on data and improve the accuracy and scientificity of decisions.

[0080] When specifically applied, the above content specifically includes:

[0081] The digital transformation hub model integrates data from various business links such as order processing, inventory management, supply chain coordination, and customer feedback to achieve centralized data management and efficient business collaboration. The nodes in the model represent business entities or processes, such as orders, inventory, suppliers, and customers; the edges represent the relationships and interactions between them, such as the association between orders and inventory, and the transactions between suppliers and customers.

[0082] The specific performance of nodes and edges is as follows:

[0083] The nodes include:

[0084] An order is a purchase request placed by a customer, including product information, quantity, price, etc.

[0085] Inventory, which refers to the number of products a business stores, is directly related to order processing.

[0086] Suppliers, which represent external entities that provide products or services, are closely related to supply chain coordination.

[0087] Customers, representing external entities that purchase products or services, are the source of customer feedback data.

[0088] Edges include:

[0089] The association between orders and inventory. When an order is created, the model will automatically check the inventory quantity and update the inventory information.

[0090] Supplier-customer transactions, which represent business transactions between suppliers and customers, are an important part of supply chain coordination.

[0091] The integrated data is mapped to the digital transformation hub model framework and associated with the corresponding nodes and edges. For example, order data is mapped to the order node, inventory data is mapped to the inventory node, and the relationship between them is mapped as an edge. When business occurs, data flows and interacts in the model. For example, when an order is created, inventory data will be reduced accordingly, and the supply chain coordination process will be triggered to ensure that the product is delivered to the customer in a timely manner. Customer feedback data will also be integrated into the model to provide companies with real-time insights into the quality of products and services. Through the digital transformation hub model, companies can automate and intelligentize business processes. For example, when an order is created, the model automatically updates inventory information and triggers the supply chain coordination process without manual intervention. This greatly improves the efficiency and accuracy of business processing. The model integrates data from various business links into a unified data storage, realizing centralized data management. This enables companies to monitor and analyze business operations in real time, and promptly identify and solve potential problems. At the same time, centralized data management also provides companies with rich data resources and analysis tools to support data-driven decision-making.

[0092] Take e-commerce companies as an example. When a customer places an order to purchase goods on the website, the digital transformation hub model will automatically process the order. First, the model will check whether the inventory quantity is sufficient. If it is sufficient, the inventory information will be updated and the corresponding quantity will be reduced; if it is insufficient, the procurement process will be triggered to replenish the inventory. At the same time, the model will coordinate all links in the supply chain to ensure that the goods can be delivered to customers in a timely manner. After the customer receives the goods, their feedback data will also be integrated into the model to provide the company with real-time insights into the quality of products and services. The flow and interaction of these data in the model realizes efficient business collaboration and centralized data management.

[0093] In a preferred embodiment of the present invention, the calculation formula of the fitness function is:

[0094]

[0095] Among them, F represents the fitness value; w3 represents the weight of inventory cost; w4 represents the weight of supply chain satisfaction; C i represents the inventory cost of the i-th iteration; η represents a constant; ζ represents the adjustment parameter of the holding cost; I h represents holding cost; L represents logistics efficiency; θ represents the adjustment parameter of supply chain satisfaction; S s represents supply chain satisfaction; ξ represents the adjustment parameter of logistics cost; It represents the parameter of balanced logistics efficiency; e represents the base of natural logarithm.

[0096] In the embodiment of the present invention, the business objectives of optimization are clearly defined, such as reducing inventory costs, improving logistics efficiency, and enhancing supply chain satisfaction. The key factors affecting the above objectives are analyzed, including inventory costs C i 、Holding Cost I h , logistics efficiency L, supply chain satisfaction S s Etc. According to the importance of business needs and goals, a weight is set for each key factor (such as w3 and w4) to reflect its relative importance in the overall evaluation. Introduce adjustment parameters (such as η, ζ, θ, ξ, ) to adjust the specific impact of each key factor in the fitness function to more flexibly reflect the complexity and dynamics of actual business scenarios. Based on the identified key factors and the set weights and parameters, a comprehensive fitness function framework is constructed. This function should be able to comprehensively and objectively reflect the quality of the business status. For each key factor, according to its characteristics and business needs, select an appropriate mathematical expression to quantify its contribution. For example, using the linear expression w3·(C i +η) to evaluate the impact of inventory costs; using an exponential function to penalize high holding costs; use a combination of linear and multiplicative w4·(L+θ·S s) to consider both logistics efficiency and supply chain satisfaction; using a quadratic function To punish the deviation of logistics efficiency and balance parameters. Integrate the mathematical expressions of each key factor into the fitness function to form a complete evaluation system. According to the actual business scenarios and needs, fine-tune and optimize the weights and parameters to ensure that the fitness function can accurately and effectively reflect the business status.

[0097] w3·(C i +η) takes into account the inventory cost and its fixed adjustment item. By setting reasonable weights w3 and adjustment items η, enterprises can be encouraged to reduce inventory costs, thereby improving capital utilization efficiency and profitability. s ) and ξ· The logistics efficiency and logistics cost are considered together. By setting appropriate weight w4, adjusting parameters θ, ξ and balance parameters It can motivate enterprises to improve logistics efficiency and control logistics costs, thereby achieving more efficient logistics operations. s ) considers the impact of supply chain satisfaction on overall business performance. By introducing the adjustment parameter θ of supply chain satisfaction, enterprises can be encouraged to pay attention to and improve the satisfaction of supply chain partners, thereby strengthening cooperative relationships and improving the stability and efficiency of the overall supply chain. Some use exponential functions to penalize high holding costs. This design can motivate companies to reduce holding costs while avoiding excessive penalties for low holding costs, thereby achieving reasonable control of holding costs. By comprehensively considering multiple key factors such as inventory costs, holding costs, logistics efficiency, and supply chain satisfaction, the fitness function formula provides a comprehensive evaluation system for companies. This helps companies make more informed decisions in a complex and changing business environment to optimize overall business performance.

[0098] In a preferred embodiment of the present invention, the above step 14, iteratively optimizing the digital transformation hub model through selection, crossover and mutation operations until a preset number of iterations is reached to obtain an optimized digital transformation hub model, may include:

[0099] Step 145, creating an initial population including multiple candidate solutions of the digital transformation hub model, each candidate solution being represented as a set of parameters;

[0100] Step 146, using the fitness function to evaluate each candidate solution, and determining the fitness value of the candidate solution from the current population as the parent;

[0101] Step 147, performing a crossover operation on the determined parent candidate solution to generate a new child candidate solution, so as to obtain a child candidate solution containing a new feature;

[0102] Step 148, performing a mutation operation on the offspring candidate solution, and using a fitness function to evaluate the newly generated offspring candidate solution to determine a corresponding fitness value;

[0103] Step 149, determine the final candidate solution based on the fitness value, and update the population until the preset number of iterations is reached, so as to obtain the optimized digital transformation hub model based on the fitness value of the candidate solution.

[0104] In an embodiment of the present invention, a population containing multiple candidate solutions of the digital transformation hub model is initialized, and each candidate solution is represented by a set of parameters. These parameters define the different characteristics of the model, thus forming the basis of the search space. The fitness function is the key to evaluating the pros and cons of the candidate solutions. It calculates a fitness value for each candidate solution based on business needs and goals, taking into account multiple factors (such as cost, efficiency, satisfaction, etc.). This value reflects the performance of the candidate solution in solving the digital transformation problem. The selection operation is based on the fitness value. The parent generation is determined according to the fitness value of the candidate solution. This ensures that excellent genes (parameters) are retained and passed on to the next generation. The crossover operation is one of the core steps in the genetic algorithm. It generates new offspring candidate solutions by exchanging or combining the genes of the parent candidate solution. In this way, the offspring candidate solution contains the excellent genes of the parent generation, and also produces new and better gene combinations. The mutation operation is to randomly change the genes of the offspring candidate solution to generate a new solution. This is to increase the diversity of solutions and find better solutions. The mutated offspring candidate solution also needs to be evaluated using the fitness function to determine its performance. According to the fitness value, the final candidate solution is determined and the population is updated. The new population consists of the parent candidate solution and the mutated child candidate solution. Then, the above steps are repeated until the preset number of iterations is reached. Through continuous iteration, the performance of the candidate solution can be gradually improved, and finally an optimized digital transformation hub model is obtained.

[0105] Through iterative optimization, the performance of candidate solutions can be gradually improved, thus obtaining an optimized digital transformation hub model. This model has better performance in solving digital transformation problems and can bring higher benefits to enterprises. Crossover and mutation operations increase the diversity of solutions. By combining different genes (parameters), new and better solutions can be generated. This helps to jump out of the local optimal solution and find the global optimal solution.

[0106] The selection operation is based on the fitness value, which ensures that excellent genes are retained and passed on to the next generation. In this way, the proportion of excellent solutions in the population will gradually increase, thereby accelerating the optimization process. Through the iterative optimization process, the model can be continuously learned and improved to adapt to the ever-changing business needs and environment. This makes the model more flexible and adaptable. The optimized digital transformation hub model can provide enterprises with more efficient and intelligent decision support. It can help enterprises better understand and solve problems in digital transformation, thereby improving their competitiveness and market position.

[0107] When specifically applied, the above content specifically includes:

[0108] In the scenario of digital transformation, initializing the population may mean creating a series of candidate solutions for the digital transformation hub model with different parameter configurations. These parameters involve data processing capabilities, system response speed, user interface friendliness, security and other aspects. The fitness function will calculate a fitness value for each candidate solution based on the specific business needs and goals of the enterprise, taking into account multiple factors such as cost, efficiency, and user satisfaction. For example, a candidate solution may obtain a higher fitness value because it has higher data processing capabilities and user satisfaction. According to the fitness value, the candidate solution with higher fitness is selected as the parent. These parents will be used in subsequent crossover operations to ensure that excellent genes (parameters) are retained and passed on to the next generation. The selected parents are crossovered to generate new child candidate solutions by exchanging or combining their genes (parameters). For example, one parent has excellent data processing capabilities, while the other has excellent user interface design. Through the crossover operation, a child candidate solution that has the advantages of both can be generated. The child candidate solution is mutated to randomly change some of its genes (parameters) to generate a new solution. This helps to increase the diversity of solutions and may find a better solution. For example, the mutation operation slightly adjusts the data processing capabilities or user interface design of a candidate solution to see if these changes have a positive impact on the fitness value. Based on the fitness value, the final candidate solution is determined and the population is updated. The new population consists of the parent candidate solution and the mutated child candidate solution. Then, the above steps are repeated until the preset number of iterations is reached. Through continuous iteration, the performance of the candidate solution can be gradually improved.

[0109] Suppose an enterprise is undergoing digital transformation and wants to optimize its customer service system. They can use genetic algorithms to optimize the digital transformation hub model to improve the efficiency and user satisfaction of the customer service system. Create a series of customer service system candidate solutions with different parameter configurations, such as response time, user interface design, data processing capacity, etc. According to the business needs and goals of the enterprise, design a fitness function that comprehensively considers multiple factors such as the efficiency, user satisfaction, and cost of the customer service system. Calculate the fitness value for each candidate solution. Select candidate solutions with higher fitness as parents, which have faster response time and good user interface design. Perform crossover operations on the parents to generate new child candidate solutions. These children may have the advantages of both parents, such as faster response time and more user-friendly interface. Perform mutation operations on the child candidate solutions and slightly adjust their parameter configurations to see if these changes have a positive impact on the fitness value. Based on the fitness value, determine the final candidate solution and update the population. Repeat the above steps until the preset number of iterations is reached. Finally, an optimized customer service system digital transformation hub model with higher efficiency and user satisfaction is obtained.

[0110] In a preferred embodiment of the present invention, the above step 15 adjusts the existing business processes of the enterprise according to the optimized digital transformation hub model, including redesigning the order processing process, optimizing the inventory management plan, and improving the supply chain coordination method to achieve the optimization of the digital transformation hub, which may include:

[0111] Step 152, reconstructing the order processing flow according to the optimized digital transformation hub model to obtain a reconstructed order processing flow;

[0112] Step 153, calculating the economic order quantity according to the reconstructed order processing flow and historical sales data to determine the inventory plan, and setting the inventory quantity and replenishment cycle according to the inventory plan;

[0113] Step 154, evaluating the execution of the reconstructed order processing flow and inventory plan through the supply chain management system to obtain an evaluation result;

[0114] Step 155, based on the evaluation results, continuously optimize and adjust the digital transformation hub model and business processes to achieve optimization of the digital transformation hub.

[0115] In an embodiment of the present invention, based on the optimized digital transformation hub model, a comprehensive analysis of the existing order processing process is performed to identify bottlenecks and inefficient links. A new order processing process is designed and implemented, which may include functions such as automated order reception, intelligent order allocation, fast order confirmation and tracking to improve processing speed and accuracy. Through the digital transformation hub model, the operation of the order processing process is monitored in real time to ensure the stability and efficiency of the process. Using the reconstructed order processing process and historical sales data, the economic order quantity (EOQ) is calculated to determine the final inventory plan. According to the inventory plan, set a reasonable inventory level and replenishment cycle to balance the relationship between inventory costs and meeting customer needs.

[0116] The digital transformation hub model can update inventory information in real time, predict future demand changes, and automatically adjust inventory plans to adapt to market changes. Through the supply chain management system (SCM), the reconstructed order processing process and inventory plan are integrated and coordinated with supply chain partners such as suppliers, manufacturers, and logistics providers.

[0117] The SCM system can monitor the operation of the supply chain in real time, including order status, inventory levels, logistics progress, etc., to ensure the smoothness and efficiency of the supply chain. The digital transformation hub model can exchange and share data with the SCM system to provide accurate and timely information support for supply chain decision-making. Through the supply chain management system, the execution of the reconstructed order processing process and inventory plan is regularly evaluated, including processing speed, accuracy, inventory turnover rate, cost savings and other indicators. Based on the evaluation results, identify existing problems and improvement points, and continuously optimize and adjust the digital transformation hub model and business processes. Through continuous optimization and adjustment, the digital transformation hub can be continuously optimized to improve the company's operational efficiency and customer satisfaction.

[0118] The reconstructed order processing process is more automated and intelligent, which can significantly improve the speed and accuracy of order processing and reduce human errors and delays. By calculating the economic order quantity and setting a reasonable inventory volume and replenishment cycle, the relationship between inventory cost and meeting customer needs can be balanced, reducing inventory cost and out-of-stock risks. Improving supply chain coordination methods can ensure the smoothness and efficiency of the supply chain, reduce the risk of supply chain disruptions and delays, and improve the company's market response speed and competitiveness. Through regular evaluation and optimization, existing problems can be continuously discovered and solved, and the digital transformation center can be continuously optimized to improve the company's overall operational efficiency and customer satisfaction.

[0119] When specifically applied, the above content specifically includes:

[0120] Use the digital transformation hub model to conduct in-depth data analysis and mining of the existing order processing process. Identify bottlenecks and inefficiencies in the process, such as manual input errors, processing delays, and information opacity. Based on the analysis results, design and implement a new order processing process, introducing automation and intelligent technologies. The new process may automate order reception (automatically receiving orders from different channels through API interfaces), intelligent order allocation (automatically allocating orders based on factors such as inventory, logistics, and customer needs), and fast order confirmation and tracking (notifying customers of order status in real time through SMS, email, or APP). Use the digital transformation hub model to monitor the operation of the new order processing process in real time to ensure the stability and efficiency of the process. Based on the monitoring data, adjust the process parameters and configuration in a timely manner to optimize the processing speed and accuracy. Use the reconstructed order processing process and historical sales data to calculate the economic order quantity (Q) to determine the final inventory plan. According to the inventory plan, set a reasonable inventory level and replenishment cycle to balance the relationship between inventory cost and meeting customer needs. Through the supply chain management system (SCM), integrate and coordinate the reconstructed order processing process and inventory plan with supply chain partners such as suppliers, manufacturers, and logistics providers. Realize real-time sharing and synchronization of supply chain information, and improve the transparency and responsiveness of the supply chain. Regularly evaluate the execution of the reconstructed order processing process and inventory plan through the SCM system, including processing speed, accuracy, inventory turnover, cost savings and other indicators. Based on the evaluation results, identify existing problems and improvement points, and continuously optimize and adjust the digital transformation hub model and business processes.

[0121] Assume a retail business is undergoing digital transformation and wants to optimize its order fulfillment process and inventory management. They can apply the above by following these steps:

[0122] The existing order processing process was analyzed using the digital transformation hub model. It was found that manual input of order information was time-consuming and error-prone, and unreasonable order allocation led to logistics delays. An automated order receiving system was introduced to automatically receive orders from different channels such as e-commerce platforms, physical stores, and mobile applications through API interfaces. An intelligent order allocation algorithm was implemented to automatically allocate orders to the nearest warehouse or store for processing based on factors such as inventory status, logistics distance, and customer demand. Fast order confirmation and tracking services were provided, and customers were notified of order status in real time through SMS, email, or APP to improve customer satisfaction. The operation of the new order processing process was monitored in real time using the digital transformation hub model, and it was found that the automated receiving system occasionally had data errors. System parameters and configurations were adjusted in a timely manner, and data verification and error handling mechanisms were optimized to ensure the stability and efficiency of the process. Based on the reconstructed order processing process and historical sales data, the economic order quantity (Q) was calculated to determine the final inventory plan. Reasonable inventory levels and replenishment cycles were set to balance the relationship between inventory costs and meeting customer needs, and reduce inventory backlogs and out-of-stock risks.

[0123] Through the supply chain management system (SCM), the reconstructed order processing process and inventory plan are integrated and coordinated with suppliers, manufacturers, logistics providers and other supply chain partners. Realize real-time sharing and synchronization of supply chain information, improve supply chain transparency and responsiveness, and reduce the risk of supply chain disruptions and delays. Regularly evaluate the execution of the reconstructed order processing process and inventory plan through the SCM system, and find significant effects such as increased processing speed, enhanced accuracy, increased inventory turnover rate and cost savings. Based on the evaluation results, continue to optimize and adjust the digital transformation hub model and business processes to achieve continuous optimization of the digital transformation hub and improve the company's operational efficiency and customer satisfaction.

[0124] In a preferred embodiment of the present invention, the calculation formula of economic order quantity is:

[0125]

[0126] Where Q represents the economic order quantity; D represents the annual demand; S represents the fixed cost of each order; C p It is expressed as the additional processing cost for each order; H represents the basic annual holding cost per unit of goods; C h It represents the additional cost per unit of commodity due to the variability of holding costs; V h The coefficient representing the variability of holding costs; C s represents the cost of each out-of-stock event; R represents the expected out-of-stock frequency.

[0127] In the embodiment of the present invention, the ordering cost includes the fixed cost (S) of each order and the additional processing cost (C p). Fixed costs S are directly related to the number of orders, including administrative costs, communication costs, document processing costs, etc. incurred during the ordering process. For example, you may need to pay handling fees, telephone charges or network fees when placing an order, as well as paper, printing and mailing costs required to process the order. These costs are fixed, that is, no matter how much you order, you need to pay these costs for each order. Therefore, reducing the number of orders is an effective way to reduce fixed costs. Additional processing costs C p It refers to the costs related to the order quantity and increases with the increase of order quantity, including the costs of inspection, sorting, packaging, and handling of ordered items. For example, when the ordered items arrive, they need to be inspected for quality, sorted by category, repackaged to suit warehouse storage, and transported to a designated location. These costs are variable and proportional to the order quantity. Therefore, when the order quantity is large, the additional handling costs will also increase accordingly. In order to reduce these costs, companies can reduce the additional handling costs of each order by optimizing the ordering process and improving processing efficiency.

[0128] These costs are proportional to the number of orders. The more orders you place, the higher the ordering costs. Therefore, reducing the number of orders can reduce ordering costs. Holding costs include the basic annual holding cost per unit of goods (H) and the additional costs caused by changes in holding costs (C h ×(1+V h )). These costs are proportional to the amount of inventory in stock; the larger the inventory, the higher the holding costs. Therefore, reducing inventory can reduce holding costs. When the inventory is insufficient to meet demand, there will be out-of-stock costs (C s ). The out-of-stock cost is related to the out-of-stock frequency (R) and the out-of-stock quantity. The existence of out-of-stock cost reminds us that the order quantity cannot be too small, otherwise it will lead to frequent out-of-stock and high out-of-stock cost. The total cost includes ordering cost, holding cost and out-of-stock cost. In practical applications, the out-of-stock cost C s It is related to the order quantity Q, because the larger the order quantity, the smaller the possibility of out-of-stock. The various parameters in the economic order quantity formula reflect the impact of different cost components on the order quantity. For example, the larger the annual demand D, the larger the order quantity Q; while the fixed cost S and the additional processing cost C p The higher the holding cost is, the smaller the order quantity Q will be, in order to reduce the number of orders and ordering costs. The basic annual holding cost H and the additional cost C caused by the change in holding cost are included in the holding cost. h ×(1+V h ) is higher, the order quantity Q will be smaller to reduce inventory and lower holding costs.

[0129] By calculating the economic order quantity, you can reduce the ordering cost. The fixed cost (S) and the additional processing cost (C) of each order are p) is proportional to the number of orders, so reducing the number of orders can significantly reduce these costs. At the same time, the holding costs are taken into account, including the base annual holding costs (H) and the additional costs C caused by changes in holding costs. h ×(1+V h ). By optimizing order quantities, companies can reduce unnecessary inventory holdings, thereby reducing holding costs. Reducing inventory holdings means that companies can free up more funds for other investments or operating activities. This helps improve the efficiency of capital utilization and the overall profitability of the company. It helps companies standardize and automate inventory management. By setting a clear economic order quantity, companies can more easily formulate procurement plans, arrange production and distribution activities, thereby improving overall operational efficiency. When companies use formulas for inventory management, they can better collaborate with upstream and downstream partners in the supply chain. By sharing inventory information and ordering plans, companies can work more closely with partners such as suppliers and distributors to jointly optimize the overall performance of the supply chain. The formula provides a scientific basis for the company's inventory management decisions. By entering different parameter values, companies can simulate different ordering strategies and evaluate their impact on total costs. This helps make more informed decisions to cope with changes in market demand and uncertainties in the supply chain.

[0130] like Figure 2 As shown, an embodiment of the present invention further provides a digital hub optimization system 20, comprising:

[0131] The acquisition module 21 is used to acquire enterprise business process data, including order processing, inventory management, supply chain coordination, and customer feedback, and pre-process the enterprise business process data to obtain a processed data pool; construct a digital transformation hub model based on the processed data pool; and define a fitness function to evaluate the performance of the current digital transformation hub model;

[0132] Processing module 22 is used to iteratively optimize the digital transformation hub model through selection, crossover and mutation operations until a preset number of iterations is reached to obtain the optimized digital transformation hub model; according to the optimized digital transformation hub model, the company's existing business processes are adjusted, including redesigning the order processing process, optimizing the inventory management plan, and improving the supply chain coordination method, so as to achieve the optimization of the digital transformation hub.

[0133] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0134] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0135] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0136] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A digital hub optimization method, characterized in that: The method comprises: Acquire enterprise business process data, including order processing, inventory management, supply chain coordination, and customer feedback, and pre-process the enterprise business process data to obtain a processed data pool; Build a digital transformation hub model based on the processed data pool; Define a fitness function to evaluate the performance of the current digital transformation hub model; Through selection, crossover and mutation operations, the digital transformation hub model is iteratively optimized until a preset number of iterations is reached to obtain an optimized digital transformation hub model; Based on the optimized digital transformation hub model, the company's existing business processes are adjusted, including redesigning the order processing process, optimizing inventory management solutions, and improving supply chain coordination methods to achieve optimization of the digital transformation hub.

2. The digital hub optimization method according to claim 1, characterized in that: Acquire enterprise business process data, including order processing, inventory management, supply chain coordination, and customer feedback, and pre-process the enterprise business process data to obtain a processed data pool, including: Extract new data generated in the business process from the enterprise business process data source in real time, and clean the extracted new data to obtain cleaned data; Based on common identification, the cleaned data is merged across data sources to form a processed data pool containing order processing, inventory management, supply chain coordination and customer feedback information.

3. The digital hub optimization method according to claim 2, characterized in that: Based on the processed data pool, build a digital transformation hub model, including: Based on the constructed data pool, the data of each business link including order processing, inventory management, supply chain coordination and customer feedback are integrated to obtain the integrated data; Determine the framework of the digital transformation hub model based on the integrated data and enterprise business processes, including determining the nodes and edges in the model; Map the integrated data to the digital transformation hub model framework to build the digital transformation hub model.

4. The digital hub optimization method according to claim 3, characterized in that: The calculation formula of the fitness function is: Among them, F represents the fitness value; w3 represents the weight of inventory cost; w4 represents the weight of supply chain satisfaction; C i represents the inventory cost of the i-th iteration; η represents a constant; ζ represents the adjustment parameter of the holding cost; I h represents holding cost; L represents logistics efficiency; θ represents the adjustment parameter of supply chain satisfaction; S s represents supply chain satisfaction; ξ represents the adjustment parameter of logistics cost; It represents the parameter of balanced logistics efficiency; e represents the base of natural logarithm.

5. The digital hub optimization method according to claim 4, characterized in that: Through selection, crossover and mutation operations, the digital transformation hub model is iteratively optimized until the preset number of iterations is reached to obtain the optimized digital transformation hub model, including: Creating an initial population of multiple candidate solutions for the digital transformation hub model, where each candidate solution is represented as a set of parameters; Each candidate solution is evaluated using the fitness function and the fitness value of the candidate solution is determined from the current population as the parent; Perform a crossover operation on the determined parent candidate solution to generate a new child candidate solution to obtain a child candidate solution containing new features; Perform mutation operation on the offspring candidate solution, and use the fitness function to evaluate the newly generated offspring candidate solution to determine the corresponding fitness value; According to the fitness value, the final candidate solution is determined and the population is updated until the preset number of iterations is reached. According to the fitness value of the candidate solution, the optimized digital transformation central model is obtained.

6. The digital hub optimization method according to claim 5, characterized in that: According to the optimized digital transformation hub model, the company's existing business processes are adjusted, including redesigning the order processing process, optimizing the inventory management plan, and improving the supply chain coordination method to achieve the optimization of the digital transformation hub, including: According to the optimized digital transformation hub model, the order processing process is reconstructed to obtain the reconstructed order processing process; Calculate the economic order quantity based on the reconstructed order processing flow and historical sales data to determine the inventory plan, and set the inventory quantity and replenishment cycle based on the inventory plan; Through the supply chain management system, the execution of the reconstructed order processing process and inventory plan is evaluated to obtain the evaluation results; Based on the evaluation results, the digital transformation hub model and business processes are continuously optimized and adjusted to achieve optimization of the digital transformation hub.

7. The digital hub optimization method according to claim 6, characterized in that: The formula for calculating economic order quantity is: Where Q represents the economic order quantity; D represents the annual demand; S represents the fixed cost of each order; C p It is expressed as the additional processing cost for each order; H represents the basic annual holding cost per unit of goods; C h It represents the additional cost per unit of goods due to the variability of holding costs; V h The coefficient representing the variability of holding costs; C s represents the cost of each out-of-stock event; R represents the expected out-of-stock frequency.

8. A digital hub optimization system, characterized in that: include: The acquisition module is used to acquire enterprise business process data, including order processing, inventory management, supply chain coordination, and customer feedback, and pre-process the enterprise business process data to obtain a processed data pool; Based on the processed data pool, build a digital transformation hub model; define a fitness function to evaluate the performance of the current digital transformation hub model; The processing module is used to iteratively optimize the digital transformation hub model through selection, crossover and mutation operations until a preset number of iterations is reached to obtain the optimized digital transformation hub model; according to the optimized digital transformation hub model, the company's existing business processes are adjusted, including redesigning the order processing process, optimizing the inventory management plan, and improving the supply chain coordination method, so as to achieve the optimization of the digital transformation hub.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images